# Edge Flow: A Tractable and Predictive Continuous-Time Model for Gradient Descent at the Edge of Stability

arXiv: https://arxiv.org/abs/2606.18080 · HTML: https://mlsanity.com/paper/2606.18080/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 28 references that are in the map.
- First posted on arXiv 16 Jun 2026.

## Builds on (most cited first, 20 of 20)

- [Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability](https://mlsanity.com/paper/2103.00065/) (2021)
- [The large learning rate phase of deep learning: the catapult mechanism](https://mlsanity.com/paper/2003.02218/) (2020)
- [Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability](https://mlsanity.com/paper/2209.15594/) (2022)
- [The Break-Even Point on Optimization Trajectories of Deep Neural Networks](https://mlsanity.com/paper/2002.09572/) (2020)
- [Understanding Gradient Descent on Edge of Stability in Deep Learning](https://mlsanity.com/paper/2205.09745/) (2022)
- [On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length](https://mlsanity.com/paper/1807.05031/) (2018)
- [Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction](https://mlsanity.com/paper/2206.07085/) (2022)
- [Understanding Optimization in Deep Learning with Central Flows](https://mlsanity.com/paper/2410.24206/) (2024)
- [Learning threshold neurons via the "edge of stability"](https://mlsanity.com/paper/2212.07469/) (2022)
- [Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability](https://mlsanity.com/paper/2305.11788/) (2023)
- [Beyond the Edge of Stability via Two-step Gradient Updates](https://mlsanity.com/paper/2206.04172/) (2022)
- [(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability](https://mlsanity.com/paper/2302.08982/) (2023)
- [Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency](https://mlsanity.com/paper/2402.15926/) (2024)
- [Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization](https://mlsanity.com/paper/2502.03435/) (2025)
- [Exact Mean Square Linear Stability Analysis for SGD](https://mlsanity.com/paper/2306.07850/) (2023)
- [Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression](https://mlsanity.com/paper/2506.02336/) (2025)
- [Rod Flow: A Continuous-Time Model for Gradient Descent at the Edge of Stability](https://mlsanity.com/paper/2602.01480/) (2026)
- [Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning](https://mlsanity.com/paper/2407.20209/) (2024)
- [On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials](https://mlsanity.com/paper/2602.14789/) (2026)
- [Understanding diffusion models requires rethinking (again) generalization](https://mlsanity.com/paper/2605.06077/) (2026)

## Built on by (most cited first, 3 of 3)

- [The Road Taken: The Role of Optimizers at the Edge of Stability](https://mlsanity.com/paper/2608.18415/) (2026)
- [Variational Structure at the Edge of Stability](https://mlsanity.com/paper/2608.21660/) (2026)
- [The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow](https://mlsanity.com/paper/2609.01034/) (2026)

## Abstract (arXiv)

Gradient descent in deep learning may operate at the edge of stability (EoS), a regime in which the largest eigenvalue of the loss Hessian hovers near the stability threshold 2/η, where η is the learning rate. Classical analysis tools such as gradient flow and the descent lemma do not apply here, motivating the search for a continuous-time model valid at EoS. We propose Edge Flow, a system of three coupled ordinary differential equations that provides a tractable, faithful, and predictive model of gradient descent dynamics at EoS. Edge Flow decomposes the dynamics into a center, an oscillation direction, and an oscillation magnitude. The center follows a modified gradient flow on a symmetrized loss; the direction tracks a top eigenvector of the Hessian via Rayleigh quotient dynamics; and the magnitude grows or decays exponentially depending on whether the sharpness exceeds or falls below the threshold 2/η. Crucially, sharpness stabilization emerges from the coupled dynamics via a self-stabilization feedback loop. Discretizing Edge Flow only requires two gradient evaluations and one Hessian--vector product at each iteration. We demonstrate empirically that Edge Flow tracks the dynamics of gradient descent at least as faithfully as previously proposed continuous-time EoS models, while in addition resolving the oscillation of the sharpness at the onset of EoS, and that it provides a principled framework for understanding and mitigating instabilities in this regime.